Enregistré dans:
Détails bibliographiques
Auteurs principaux: Safa, Abdulfattah, Kapanadze, Tamta, Uzunoğlu, Arda, Şahin, Gözde Gül
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.18529
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915881956671488
author Safa, Abdulfattah
Kapanadze, Tamta
Uzunoğlu, Arda
Şahin, Gözde Gül
author_facet Safa, Abdulfattah
Kapanadze, Tamta
Uzunoğlu, Arda
Şahin, Gözde Gül
contents Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging for current NLP systems. Robust understanding of such instructions is essential for deploying LLMs as general-purpose agents that can be programmed in natural language to perform complex, real-world tasks across domains like robotics, business automation, and interactive systems. Despite growing interest in this area, there is a lack of a comprehensive survey that systematically analyzes the landscape of complex instruction understanding and processing. Through a systematic review of the literature, we analyze available resources, representation schemes, and downstream tasks related to instructional text. Our study examines 181 papers, identifying trends, challenges, and opportunities in this emerging field. We provide AI/NLP researchers with essential background knowledge and a unified view of various approaches to complex instruction understanding, bridging gaps between different research directions and highlighting future research opportunities.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18529
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents
Safa, Abdulfattah
Kapanadze, Tamta
Uzunoğlu, Arda
Şahin, Gözde Gül
Computation and Language
Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging for current NLP systems. Robust understanding of such instructions is essential for deploying LLMs as general-purpose agents that can be programmed in natural language to perform complex, real-world tasks across domains like robotics, business automation, and interactive systems. Despite growing interest in this area, there is a lack of a comprehensive survey that systematically analyzes the landscape of complex instruction understanding and processing. Through a systematic review of the literature, we analyze available resources, representation schemes, and downstream tasks related to instructional text. Our study examines 181 papers, identifying trends, challenges, and opportunities in this emerging field. We provide AI/NLP researchers with essential background knowledge and a unified view of various approaches to complex instruction understanding, bridging gaps between different research directions and highlighting future research opportunities.
title Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents
topic Computation and Language
url https://arxiv.org/abs/2410.18529